© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169062
    Prev
    Next
    INDEX
    Explanations

    human society

    np_acts-logits-general · gemini-2.5-flash-lite

    nationality and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tommy
    0.50
    SEC
    0.50
    Ｓ
    0.50
    SP
    0.49
    SEQ
    0.49
    IX
    0.48
     বিবৃতিতে
    0.48
    GO
    0.47
    STAT
    0.47
    stmt
    0.46
    POSITIVE LOGITS
     différences
    0.54
     snowy
    0.50
    捂
    0.46
     praying
    0.46
     numerosos
    0.46
    ogany
    0.45
    त्रे
    0.43
    欢
    0.43
     bustling
    0.43
     ประเทศ
    0.42
    Activations Density 0.001%

    No Known Activations